Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "directed" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    directed to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     présidenti
    -0.57
     Италијани
    -0.55
     Económica
    -0.50
    󠁮
    -0.47
     comprom
    -0.46
     marinho
    -0.46
    IFORN
    -0.46
    Swap
    -0.45
    smb
    -0.45
    prevState
    -0.44
    POSITIVE LOGITS
     direction
    0.91
     directed
    0.90
     directing
    0.86
     Directed
    0.82
     Directions
    0.81
     directs
    0.81
     directives
    0.80
     Direction
    0.80
     directions
    0.80
    directed
    0.78
    Act Density 0.010%

    No Known Activations